Abstract

In this paper, we investigate brain hallucination, or gener- ating a high resolution brain image from an input low-resolution image, with the help of another high resolution brain image. Contrary to in- terpolation techniques, the reconstruction process is based on a physical model of image acquisition. Our contribution is a new regularization approach that uses an example-based framework integrating non-local similarity constraints to handle in a better way repetitive structures and texture. The effectiveness of our approach is demonstrated by experi- ments on realistic Magnetic Resonance brain images generating automat- ically high-quality hallucinated brain images from low-resolution input.